© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57373
    Prev
    Next
    INDEX
    Explanations

    colors and countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĸ®
    -0.10
    çĶľçĶľ
    -0.09
    æļĤç¼ĵ
    -0.09
    ÑģÑĤвÑĥ
    -0.08
    æĵ¦æĭŃ
    -0.08
    ummies
    -0.08
    èµ°è·¯
    -0.08
    duc
    -0.08
    çŤ
    -0.08
    Moving
    -0.08
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.13
    éĿĴ
    0.12
    èĪ¬
    0.10
    è¿Ļæł·çļĦ
    0.10
    è¿Ļæł·
    0.09
    éĤ£æł·
    0.09
    绿
    0.09
    ä¼¼çļĦ
    0.08
    è¿Ļæł·çļĦè¯Ŀ
    0.08
     Bis
    0.08
    Activations Density 0.076%

    No Known Activations